hyperfx-ai/marketing-skills

google-sheets

Safe workflow for reading, mapping, and writing Google Sheets without shifting columns or overwriting the wrong ranges.

查看源码
仓库原始内容

按源仓库内容呈现,保留标题、案例、代码、表格、链接以及原文引用的演示图片。

Google Sheets Writing

Use this skill whenever you need to write structured data into an existing spreadsheet.

Requirements

Core Rule

Never write to Google Sheets from guessed column letters alone.

Always:

  1. inspect the workbook and target worksheet
  2. find the real header row
  3. map fields by header name
  4. verify the destination range
  5. write
  6. read back sample rows to confirm alignment

Critical Failure Modes To Avoid

  • Do not assume row 1 is the real header row.
  • Do not assume column A is the first business/data column.
  • Do not treat helper cells like Total, notes, formulas, merged labels, or spacer columns as real headers.
  • Do not overwrite a broad range before checking existing data and layout.
  • Do not claim success until you read back the written cells.

Required Workflow

Step 1: Inspect workbook structure

Start with:

  • google_sheets_get
  • google_sheets_worksheets_list if needed

Confirm:

  • worksheet title
  • row/column counts
  • whether there are multiple candidate tabs

Step 2: Read enough context to find the real headers

Read more than one row when structure is unknown.

Typical pattern:

  • google_sheets_values_get(..., range="Sheet1!A1:Z5")

Look for:

  • true column labels
  • helper columns before the real table
  • title rows, totals, formulas, blank separators

If the first row contains labels like Total, Notes, or other non-record metadata, do not anchor your write range to that row alone.

Step 3: Build a header map

Map your source fields to actual sheet headers by name, not memory.

Example:

  • source field business_name -> sheet header Business Name
  • source field contact_email -> sheet header Owner (s) Email

If a required header is missing or ambiguous, stop and ask the user instead of guessing.

Step 4: Choose the safest write strategy

Use:

  • google_sheets_values_update for one verified contiguous range
  • google_sheets_values_batch_update for multiple verified ranges

Prefer narrow writes over large blanket writes.

If appending records into a table that already has fixed columns, compute the exact destination columns from the header map first.

Write Rules

  • Only write columns you have positively mapped.
  • Leave unrelated columns untouched.
  • When a sheet contains helper columns before the table, start writing at the true mapped column, not column A.
  • If a field is intentionally blank, write a blank value only to that verified column.
  • Use RAW unless the user explicitly wants formulas or Sheets parsing behavior.

Verification Is Mandatory

Immediately after writing:

  1. read back the exact written range
  2. inspect at least 2-3 sample rows
  3. confirm each field landed under the intended header

If the read-back is misaligned, acknowledge it and correct it before reporting success.

Recommended Tool Pattern

  1. google_sheets_get
  2. google_sheets_values_get on a header-discovery range such as A1:Z5
  3. optional google_sheets_values_batch_get for existing data + destination area
  4. google_sheets_values_update or google_sheets_values_batch_update
  5. google_sheets_values_get on the written range for verification

Example Mindset

Bad:

  • “I saw Business Name near the start, so I will write A2:F51.”

Good:

  • “The first visible row includes Total: 7 in column A, while Business Name is actually in column B, so I will map the write range from B onward and verify it after writing.”
来自同一仓库

更多 Skills

全部 Skills
hyperfx-ai
社区

ad-creative-generation

Generate on-brand ad creatives — visuals + copy — for Google, Meta (Facebook / Instagram), and other paid platforms via the Hyper MCP. Extracts brand identity from a website, writes ad copy variants, and produces brand-consistent images using reference-based image generation. Use when the user asks for ad creative, ad copy variants, RSA headlines, Meta ad creative, display ads, carousel ads, or A/B test variants.

安装量
1
GitHub Stars
83
最近更新
8月25日
hyperfx-ai
社区

amazon-ads

Plan and create Amazon Sponsored Products campaigns end-to-end via the Hyper MCP. Use when the user wants to launch Amazon Ads, set up Sponsored Products, manage keyword targeting and bids, configure ASIN or category product targeting, add negative keywords, automate budget rules, analyze ACoS / ROAS, or generate Sponsored Products reports. Also triggers on amazon ppc, amazon campaign, amazon keywords, or amazon report.

安装量
1
GitHub Stars
83
最近更新
8月25日
hyperfx-ai
社区

analytics-insights

Drive Google Analytics (GA4), Google Tag Manager, Google Search Console, and BigQuery from chat — tracking plans, GA4 reports, key-event (conversion) setup, custom dimensions and metrics, GTM audits, GSC performance, and GA4 BigQuery export queries. Use when the user wants an analytics audit, a GA4 report, a tracking plan, conversion setup, GTM cleanup, search-performance data, or asks "how is the site performing?" or "are my conversions firing?".

安装量
1
GitHub Stars
83
最近更新
8月25日
hyperfx-ai
社区

blog-generation

Generate one excellent, on-brand blog post per run for any business, built to rank on Google and get cited by AI search (ChatGPT, Claude, Perplexity, AI Overviews). A stateful engine: reads a brand strategy doc, picks a fresh topic (never repeats), researches, writes in the brand's voice, and logs the post back. Use when the user wants to write a blog post, run a daily or recurring blog task, or generate SEO / AEO / blog content. For keyword data and audits, defer to seo-research.

安装量
1
GitHub Stars
83
最近更新
8月25日